Missense-depleted regions in population exomes implicate ras superfamily nucleotide-binding protein alteration in patients with brain malformation

Abstract

Genomic sequence interpretation can miss clinically relevant missense variants for several reasons. Rare missense variants are numerous in the exome and difficult to prioritise. Affected genes may also not have existing disease association. To improve variant prioritisation, we leverage population exome data to identify intragenic missense-depleted regions (MDRs) genome-wide that may be important in disease. We then use missense depletion analyses to help prioritise undiagnosed disease exome variants. We demonstrate application of this strategy to identify a novel gene association for human brain malformation. We identified de novo missense variants that affect the GDP/GTP-binding site of ARF1 in three unrelated patients. Corresponding functional analysis suggests ARF1 GDP/GTP-activation is affected by the specific missense mutations associated with heterotopia. These findings expand the genetic pathway underpinning neurologic disease that classically includes FLNA. ARF1 along with ARFGEF2 add further evidence implicating ARF/GEFs in the brain. Using functional ontology, top MDR-containing genes were highly enriched for nucleotide-binding function, suggesting these may be candidates for human disease. Routine consideration of MDR in the interpretation of exome data for rare diseases may help identify strong genetic factors for many severe conditions, infertility/reduction in reproductive capability, and embryonic conditions contributing to preterm loss.

Keywords: ARF1; Exome sequencing; GDP/GTP; MDR; RAS superfamily; brain malformation; missense-depletion; nucleotide-binding; variant prioritization.

Figure 1

Missense depletion of genes by disease inheritance pattern. Violin plots of dN/dS for disease genes by inheritance annotation (OMIM and Orphanet). AD, autosomal dominant; AR, autosomal recessive, XL, X-linked. P<2.2e−16, Kruskal–Wallis rank sum test.

Figure 2

Missense-depleted regions in genes using population exomes. (a) Missense variant site density plots along the coding sequence length of ACTB or SMARCA4 from ~6,500 sequenced exomes from ESP. Grey-shaded regions indicate candidate missense-depleted regions (MDRs) that lack missense variants but that have synonymous variants. (b) Missense variant plots for ACTB and SMARCA4 using ~60,000 exomes from ExAC data, further delineate MDRs. (c) Density plots of pathogenic missense variant sites from ClinVar.

Figure 3

Prioritisation of variant-affected genes from the proband. Comparison of variant-affected genes from the proband (vertical lines) compared with the distribution for all genes in the exome (histogram). (a) Evaluation by dN/dS from population exomes, a lower score indicates higher priority. (b) Evaluation using Earthmover's distance, a measure for potential MDR-containing gene. Candidates ARF1, SEPT7 and SOD1 are highlighted in coloured vertical lines.

Figure 4

Localisation of variants on ARF1. In blue, location of de novo heterozygous c.103T>C (p.Y35H), de novo heterozygous variant c.296G>A (p.R99H), and de novo heterozygous c.379A>G (p.K127E) from cases. De novo missense variants in ARF1 from brain malformation cases are localised near the GDP-binding site of ARF1 in contrast to the variants found in the ExAC population (dark grey numbers). Colours: ARF1 (orange) and the ARFGEF Sec7 domain, GDP (light blue) and Mg2⁺. (a, b) are different views of ARF1. Structure from protein database accession 1R8Q.

Figure 5

Variant in ARF1 alters nucleotide activation. ARF1 nucleotide activation of wildtype (WT) or p.Y35H ARF1-transfected 293T cells. 293T cells basal ARF1 expression (lane 1), and wildtype and p.Y35H transfection demonstrate similar ARF1 expression (lanes 2 and 3). Blank (lane 4) Pulldown for GTP-activated ARF1 (lanes 5–9): Basal activated ARF1 (lane 7). Compared to activated ARF1 levels in WT (lane 8), p.Y35H variant demonstrates reduced GTP activation (lane 9). Lanes 1–3 represent the protein expression for the assay. Lanes 5–6 represent the positive and negative controls (GTP-gamma-S and GDP, respectively). Result is representative for three independent transfection experiments with pulldown and western blotting.